[jrflo]

Agreed. GPT 5.5 will come up with more straightforward solutions with far fewer tokens than Claude. Also, the usage limits are much more generous for Codex than Claude Code for the same monthly plan.

[mikeshi42]

I've been using both and as far as I can tell with ccusage, the $ equivalent budgets are about the same between them now. This may have been true before anthropic doubled their quotas and openai 2x promo expired last month.

[SmolSpideritito]

How are you finding it now? I have been deciding between 20 dollar subscriptions for GPT, Claude, and Cursor (Grok 4.5) respectively

[mattmanser]

Last time I used Codex it would make loads of assumptions, often quite big ones, without asking.

Did they fix that, as that for me was what actually made codex worse.

[arcanemachiner]

I find that I have to tell GPT and Claude to keep asking me questions, or they will just fill in the gaps themselves (wrongly).

[dboreham]

My experience has been that Claude/Opus will ask me questions, although sometimes I have to step in and redirect a bit. Codex/GPT just dives in and cranks code out, which after using Claude for a year I found rather concerning. It wrote working code though. Claude/Fable does something similar (asks far fewer questions than Opus) fwiw.

[nico1207]

Did you use plan mode?